Question: Can we autodetect meaningful features.
Feature Engineering is an ad-hoc manual process that depends on domain knowledge, intuition, data exploration, and creativity. However, this process is dataset-dependent, time-consuming, tedious, subjective, and not a scalable solution.
Automated Feature Creation automatically generates features using a framework; these features can be filtered using Feature Selection to avoid feature explosion.
Below are some popular open-source libraries for automated feature engineering:
- Pycaret – PyCaret
- Featuretools for advanced usage – Home | What is Featuretools? — Featuretools 1.1.0 documentation
- Optuna – A hyperparameter optimization framework
- Feature-engine – A Python library for Feature Engineering for Machine Learning — 1.1.2
- ExploreKit – GitHub – giladkatz/ExploreKit
- https://www.turintech.ai/blog/feature-generation-what-it-is-and-how-to-do-it